Downloads · 30 days
14
18% of all-time downloads
gemma-4-12B-it-RotorQuant-MLX-MXFP4
majentik/gemma-4-12B-it-RotorQuant-MLX-MXFP4
gemma-4-12B-it-RotorQuant-MLX-MXFP4 is a image-text-to-text model from majentik. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as gemma.
google/gemma-4-12B-it @ 12ace6d648d72bd41519e140f1185f34d38c7e3d quantized pack, published as majentik/gemma-4-12B-it-RotorQuant-MLX-MXFP4.
All-time downloads
79
Public
Parameters
12B
6.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.4 GB · 99%
Parameter types
How the weights are stored.
U3212B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-4-12B-it — RotorQuant MLX MXFP4
google/gemma-4-12B-it @ 12ace6d648d72bd41519e140f1185f34d38c7e3d quantized pack, published as majentik/gemma-4-12B-it-RotorQuant-MLX-MXFP4.
Method
MLX quantization via mlx-vlm 0.6.3 (MXFP4, group_size 32); vision + audio towers retained in BF16 (not quantized).
Release line
Released under the RotorQuant line. RotorQuant and TurboQuant are this project's release labels for this pack, not distinct quantization algorithms — both brand repos for a given tier carry byte-identical weights, produced once and published under two names. No brand-specific speedup is claimed or measured for either label.
Modality
This pack is image-text-to-text capable: the vision and audio towers ship in BF16 alongside the quantized text tower, so image (and audio) inputs are supported end to end via mlx-vlm.
Vision fidelity note: for this instruct variant, vision has only been validated at 6-bit and 8-bit. Vision fidelity degrades below 6-bit; use 6-bit or 8-bit for image tasks.
License
Governed by the Gemma Terms of Use. See the upstream repo for the full license text.
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- gemma4_unified
- License
- gemma
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026